Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/132950
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Optimal robust formation control for heterogeneous multi-agent systems based on reinforcement learning |
Author: | Yan, B. Shi, P. Lim, C.C. Shi, Z. |
Citation: | International Journal of Robust and Nonlinear Control, 2022; 32(5):2683-2704 |
Publisher: | Wiley |
Issue Date: | 2022 |
ISSN: | 1049-8923 1099-1239 |
Statement of Responsibility: | Bing Yan, Peng Shi, Cheng-Chew Lim, Zhiyuan Shi |
Abstract: | In this paper, a reinforcement learning-based robust control strategy is proposed for uncertain heterogeneous multi-agent systems to achieve optimal collision-free time-varying formations. Without using any global information, a fully distributed adaptive observer is developed to estimate both dynamics and states of the reference and disturbance systems. The observer parameters are found by an observed model-based or a model-free off-policy reinforcement learning algorithm. Using the internal model principle, a novel optimal robust formation control strategy is developed based on another proposed off-policy reinforcement learning algorithm. The algorithm addresses the non-quadratic optimization problem when the system model is completely unknown. Taking the bushfire edge tracking and patrolling task for an unmanned aerial vehicle-unmanned ground vehicle heterogeneous system as an example, the effectiveness, and robustness of the developed control strategy are verified by simulations. |
Keywords: | Adaptive observer; heterogeneous multi-agent systems; reinforcement learning; robust formation control |
Description: | First published: 13 October 2021 |
Rights: | © 2021 John Wiley & Sons Ltd. |
DOI: | 10.1002/rnc.5828 |
Grant ID: | http://purl.org/au-research/grants/arc/DP170102644 |
Published version: | http://dx.doi.org/10.1002/rnc.5828 |
Appears in Collections: | Electrical and Electronic Engineering publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.